Real-time and offline techniques for identifying obstructive sleep apnea patients

Obstructive Sleep Apnea (OSA) is a common sleeping disorder in which persons temporarily stop breathing during their sleep. Untreated OSA may lead to several cardio vascular diseases, diabetes, stroke etc. Currently, overnight Polysomnography (PSG) is the widely used technique to detect sleep apnoea. However, a human expert has to monitor the patient overnight. In this paper, we use the technique of motif discovery to identify long term patterns in vital parameters obtained from a combination of smart phones and body attached sensors. We further extend this work to use hamming distance technique to identify similar patients for case based reasoning. Using this, we reduce the need for having expert intervention. As an initial implementation, we have tested our motif discovery technique on Physionet sleep apnea dataset of ECG and SpO2.